metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: apv53-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.78
apv53-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.5072
- Accuracy: 0.78
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3311 | 1.0 | 113 | 1.2307 | 0.67 |
| 0.7706 | 2.0 | 226 | 1.0825 | 0.63 |
| 0.7012 | 3.0 | 339 | 0.8888 | 0.75 |
| 0.3658 | 4.0 | 452 | 0.7326 | 0.78 |
| 0.4113 | 5.0 | 565 | 0.9069 | 0.73 |
| 0.0964 | 6.0 | 678 | 0.8265 | 0.82 |
| 0.1707 | 7.0 | 791 | 0.8793 | 0.82 |
| 0.0078 | 8.0 | 904 | 1.2400 | 0.81 |
| 0.0136 | 9.0 | 1017 | 1.1516 | 0.79 |
| 0.0029 | 10.0 | 1130 | 1.5072 | 0.78 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0